guizang-ppt
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill accepts user input to generate a design brief, which is then processed by specialized tools. * Ingestion points: The user's message is treated as a brief in SKILL.md. * Boundary markers: No explicit separators or instructions to ignore embedded commands are used. * Capability inventory: The skill has access to file-editing tools and registration tools in SKILL.md. * Sanitization: No input validation or escaping is specified in the instructions.
Audit Metadata